Customize dataset so that Dataloader can apply…

def __len__(self):
    return len(self.data)  # Total number of samples

def __getitem__(self, idx):
    # Return one sample (image, text) at given index
    return self.data[idx]['image'], self.data[idx]['text']`

import torch
from torch.utils.data import Dataset, DataLoader
from torchvision import transforms
from PIL import Image

class ImageTextDataset(Dataset):
    def __init__(
        self, 
        data,  # List of {'image': image_path, 'text': description}
        image_transform=None,
        text_transform=None
    ):

        self.data = data

        # Optional image transformations
        if image_transform is None:
            self.image_transform = transforms.Compose([
                transforms.Resize((224, 224)),
                transforms.ToTensor(),
                transforms.Normalize(
                    mean=[0.485, 0.456, 0.406],
                    std=[0.229, 0.224, 0.225]
                )
            ])
        else:
            self.image_transform = image_transform

        # Optional text transformations
        self.text_transform = text_transform or (lambda x: x)

    def __len__(self):
        """
        REQUIREMENT 1: Return total number of samples
        - Called by DataLoader to determine dataset size
        - Used for iterations, batching
        """
        return len(self.data)

    def __getitem__(self, idx):
        """
        REQUIREMENT 2: Return a single sample
        - Called by DataLoader for each batch
        - Must return consistent data types
        - Handle potential loading errors
        """
        # Fetch data for specific index
        sample = self.data[idx]

        # Load and transform image
        try:
            image = Image.open(sample['image']).convert('RGB')
            image = self.image_transform(image)
        except Exception as e:
            print(f"Error loading image: {sample['image']}")
            # Fallback to zero tensor
            image = torch.zeros(3, 224, 224)

        # Transform text
        text = self.text_transform(sample['text'])

        return image, text

# Usage example
def main():
    # Sample data structure
    data = [
        {'image': 'path/to/image1.jpg', 'text': 'Description 1'},
        {'image': 'path/to/image2.jpg', 'text': 'Description 2'}
    ]

    # Create dataset
    dataset = ImageTextDataset(data)

    # Create DataLoader
    dataloader = DataLoader(
        dataset,
        batch_size=2,  # Number of samples per batch
        shuffle=True,  # Randomize order
        num_workers=2  # Parallel data loading
    )

    # Iterate through data
    for batch_images, batch_texts in dataloader:
        print("Batch images shape:", batch_images.shape)
        print("Batch texts:", batch_texts)
        break  # Just show first batch

if __name__ == '__main__':
    main()

# Additional optional enhancements
class EnhancedImageTextDataset(ImageTextDataset):
    def __init__(self, data, image_dir=None):
        """
        Optional: Add more flexibility
        - Prepend image directory
        - More robust path handling
        """
        if image_dir:
            data = [{
                'image': os.path.join(image_dir, item['image']),
                'text': item['text']
            } for item in data]

        super().__init__(data)